Abstract
Feature point tracking over a video sequence fails when the points go out of the field of view or behind other objects. In this paper, we extend such interrupted tracking by imposing the constraint that under the affine camera model all feature trajectories should be in an affine space. Our method consists of iterations for optimally extending the trajectories and for optimally estimating the affine space, coupled with an outlier removal process. Using real video images, we demonstrate that our method can restore a sufficient number of trajectories for detailed 3-D reconstruction.
Chapter PDF
Similar content being viewed by others
Keywords
These keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.
References
Brandt, S.: Closed-form solutions for affine reconstruction under missing data. In: Proc. Statistical Methods in Video Processing Workshop, Copenhagen, Denmark, June, 2002, pp. 109–114 (2002)
Fischer, M.A., Bolles, R.C.: Random sample consensus: A paradigm for model fitting with applications to image analysis and automated cartography. Comm. ACM 24(6), 381–395 (1981-1986)
Hartley, R., Zisserman, A.: Multiple View Geometry in Computer Vision. Cambridge University Press, Cambridge (2000)
Huynh, D.Q., Heyden, A.: Outlier detection in video sequences under affine projection. In: Proc. IEEE Conf. Comput. Vision Pattern Recog., Kauai, HI, U.S.A, December 2001, vol. 2, pp. 695–701 (2001)
Jacobs, D.W.: Linear fitting with missing data for structure-from-motion. Comput. Vision Image Understand 82(1), 57–81 (2001)
Kahl, F., Heyden, A.: Affine structure and motion from points, lines and conics. Int. J. Comput. Vision 33(3), 163–180 (1999)
Kanatani, K.: Motion segmentation by subspace separation and model selection. In: Proc. 8th Int. Conf. Comput. Vision, Vancouver, Canada, July 2001, vol. 2, pp. 301–306 (2001)
Kanatani, K.: Motion segmentation by subspace separation: Model selection and reliability evaluation. Int. J. Image Graphics 2(2), 179–197 (2002)
Kanatani, K.: Evaluation and selection of models for motion segmentation. In: Heyden, A., Sparr, G., Nielsen, M., Johansen, P. (eds.) ECCV 2002. LNCS, vol. 2352, pp. 335–349. Springer, Heidelberg (2002)
Poelman, C.J., Kanade, T.: A paraperspective factorization method for shape and motion recovery. IEEE Trans. Patt. Anal. Mach. Intell. 19(3), 206–218 (1997)
Rousseeuw, P.J., Leroy, A.M.: Robust Regression and Outlier Detection. Wiley, New York (1987)
Saito, H., Kamijima, S.: Factorization method using interpolated feature tracking via projective geometry. In: Proc. 14th British Machine Vision Conf., Norwich, UK, September 2003, vol. 2, pp. 449–458 (2003)
Shum, H.-Y., Ikeuchi, K., Reddy, R.: Principal component analysis with missing data and its application to polyhedral object modeling. IEEE Trans. Patt. Anal. Mach. Intell. 17(3), 854–867 (1995)
Sugaya, Y., Kanatani, K.: Outlier removal for motion tracking by subspace separation. IEICE Trans. Inf. Syst. E86-D(6), 1095–1102 (2003)
Tomasi, C., Kanade, T.: Shape and motion from image streams under orthography—A factorization method. Int. J. Comput. Vision 9(2), 137–154 (1992)
Tomasi, C., Kanade, T.: Detection and Tracking of Point Features, CMU Tech. Rep. CMU-CS-91-132, (April 1991), http://vision.stanford.edu/~birch/klt/
Author information
Authors and Affiliations
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2004 Springer-Verlag Berlin Heidelberg
About this paper
Cite this paper
Sugaya, Y., Kanatani, K. (2004). Extending Interrupted Feature Point Tracking for 3-D Affine Reconstruction. In: Pajdla, T., Matas, J. (eds) Computer Vision - ECCV 2004. ECCV 2004. Lecture Notes in Computer Science, vol 3021. Springer, Berlin, Heidelberg. https://doi.org/10.1007/978-3-540-24670-1_24
Download citation
DOI: https://doi.org/10.1007/978-3-540-24670-1_24
Publisher Name: Springer, Berlin, Heidelberg
Print ISBN: 978-3-540-21984-2
Online ISBN: 978-3-540-24670-1
eBook Packages: Springer Book Archive